© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11987
    Prev
    Next
    INDEX
    Explanations

    we are/have/supply/offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     needing
    -0.09
    ä¹°äºĨ
    -0.08
     Tor
    -0.08
    æĻ°
    -0.08
    ä½ıäºĨ
    -0.08
    è¿ĺéľĢè¦ģ
    -0.08
    éģĩåĪ°äºĨ
    -0.07
     they
    -0.07
     DIY
    -0.07
    8
    -0.07
    POSITIVE LOGITS
    çĭ¬çī¹
    0.11
    åĽłåľ°
    0.11
    æ´ŀå¯Ł
    0.10
    ëĦIJ
    0.10
    åı®
    0.10
    åłł
    0.10
    å®ŀäºĭæ±Ĥæĺ¯
    0.10
    æĹĹä¸ĭçļĦ
    0.10
    ä¸īåĪĨ
    0.10
    Ľå»º
    0.09
    Activations Density 0.057%

    No Known Activations